1. L4GM: Large 4D Gaussian Reconstruction Model
- Author
-
Ren, Jiawei, Xie, Kevin, Mirzaei, Ashkan, Liang, Hanxue, Zeng, Xiaohui, Kreis, Karsten, Liu, Ziwei, Torralba, Antonio, Fidler, Sanja, Kim, Seung Wook, and Ling, Huan
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning - Abstract
We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Key to our success is a novel dataset of multiview videos containing curated, rendered animated objects from Objaverse. This dataset depicts 44K diverse objects with 110K animations rendered in 48 viewpoints, resulting in 12M videos with a total of 300M frames. We keep our L4GM simple for scalability and build directly on top of LGM, a pretrained 3D Large Reconstruction Model that outputs 3D Gaussian ellipsoids from multiview image input. L4GM outputs a per-frame 3D Gaussian Splatting representation from video frames sampled at a low fps and then upsamples the representation to a higher fps to achieve temporal smoothness. We add temporal self-attention layers to the base LGM to help it learn consistency across time, and utilize a per-timestep multiview rendering loss to train the model. The representation is upsampled to a higher framerate by training an interpolation model which produces intermediate 3D Gaussian representations. We showcase that L4GM that is only trained on synthetic data generalizes extremely well on in-the-wild videos, producing high quality animated 3D assets., Comment: Project page: https://research.nvidia.com/labs/toronto-ai/l4gm
- Published
- 2024